ret <8 x i32> %t5
}
+define <8 x i32> @t1_vec_splat_undef(<8 x i32> %x, <8 x i32> %nbits) {
+; CHECK-LABEL: @t1_vec_splat_undef(
+; CHECK-NEXT: [[T0:%.*]] = add <8 x i32> [[NBITS:%.*]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+; CHECK-NEXT: [[T1:%.*]] = shl <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 undef, i32 1>, [[T0]]
+; CHECK-NEXT: [[T2:%.*]] = add <8 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+; CHECK-NEXT: [[T4:%.*]] = sub <8 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 undef, i32 32>, [[NBITS]]
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T1]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T2]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T4]])
+; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T4]]
+; CHECK-NEXT: [[T5:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 0, i32 2147483647>
+; CHECK-NEXT: ret <8 x i32> [[T5]]
+;
+ %t0 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+ %t1 = shl <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 undef, i32 1>, %t0
+ %t2 = add <8 x i32> %t1, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+ %t3 = and <8 x i32> %t2, %x
+ %t4 = sub <8 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 undef, i32 32>, %nbits
+ call void @use8xi32(<8 x i32> %t0)
+ call void @use8xi32(<8 x i32> %t1)
+ call void @use8xi32(<8 x i32> %t2)
+ call void @use8xi32(<8 x i32> %t4)
+ %t5 = shl <8 x i32> %t3, %t4
+ ret <8 x i32> %t5
+}
+
define <8 x i32> @t2_vec_nonsplat(<8 x i32> %x, <8 x i32> %nbits) {
; CHECK-LABEL: @t2_vec_nonsplat(
; CHECK-NEXT: [[T0:%.*]] = add <8 x i32> [[NBITS:%.*]], <i32 -33, i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32>
ret <8 x i32> %t5
}
+define <8 x i32> @t1_vec_splat_undef(<8 x i32> %x, <8 x i32> %nbits) {
+; CHECK-LABEL: @t1_vec_splat_undef(
+; CHECK-NEXT: [[T0:%.*]] = add <8 x i32> [[NBITS:%.*]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+; CHECK-NEXT: [[T1:%.*]] = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>, [[T0]]
+; CHECK-NEXT: [[T2:%.*]] = xor <8 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+; CHECK-NEXT: [[T4:%.*]] = sub <8 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 undef, i32 32>, [[NBITS]]
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T1]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T2]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T4]])
+; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T4]]
+; CHECK-NEXT: [[T5:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 0, i32 2147483647>
+; CHECK-NEXT: ret <8 x i32> [[T5]]
+;
+ %t0 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+ %t1 = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>, %t0
+ %t2 = xor <8 x i32> %t1, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+ %t3 = and <8 x i32> %t2, %x
+ %t4 = sub <8 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 undef, i32 32>, %nbits
+ call void @use8xi32(<8 x i32> %t0)
+ call void @use8xi32(<8 x i32> %t1)
+ call void @use8xi32(<8 x i32> %t2)
+ call void @use8xi32(<8 x i32> %t4)
+ %t5 = shl <8 x i32> %t3, %t4
+ ret <8 x i32> %t5
+}
+
define <8 x i32> @t2_vec_nonsplat(<8 x i32> %x, <8 x i32> %nbits) {
; CHECK-LABEL: @t2_vec_nonsplat(
; CHECK-NEXT: [[T0:%.*]] = add <8 x i32> [[NBITS:%.*]], <i32 -33, i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32>
ret <8 x i32> %t3
}
+define <8 x i32> @t1_vec_splat_undef(<8 x i32> %x, <8 x i32> %nbits) {
+; CHECK-LABEL: @t1_vec_splat_undef(
+; CHECK-NEXT: [[T0:%.*]] = lshr <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>, [[NBITS:%.*]]
+; CHECK-NEXT: [[T2:%.*]] = add <8 x i32> [[NBITS]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T2]])
+; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T2]]
+; CHECK-NEXT: [[T3:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 -1, i32 2147483647>
+; CHECK-NEXT: ret <8 x i32> [[T3]]
+;
+ %t0 = lshr <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>, %nbits
+ %t1 = and <8 x i32> %t0, %x
+ %t2 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+ call void @use8xi32(<8 x i32> %t0)
+ call void @use8xi32(<8 x i32> %t2)
+ %t3 = shl <8 x i32> %t1, %t2 ; shift is smaller than mask
+ ret <8 x i32> %t3
+}
+
define <8 x i32> @t1_vec_nonsplat(<8 x i32> %x, <8 x i32> %nbits) {
; CHECK-LABEL: @t1_vec_nonsplat(
; CHECK-NEXT: [[T0:%.*]] = lshr <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, [[NBITS:%.*]]
ret <8 x i32> %t4
}
+define <8 x i32> @t2_vec_splat_undef(<8 x i32> %x, <8 x i32> %nbits) {
+; CHECK-LABEL: @t2_vec_splat_undef(
+; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>, [[NBITS:%.*]]
+; CHECK-NEXT: [[T1:%.*]] = lshr <8 x i32> [[T0]], [[NBITS]]
+; CHECK-NEXT: [[T3:%.*]] = add <8 x i32> [[NBITS]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T1]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T3]])
+; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T3]]
+; CHECK-NEXT: [[T4:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 -1, i32 2147483647>
+; CHECK-NEXT: ret <8 x i32> [[T4]]
+;
+ %t0 = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>, %nbits
+ %t1 = lshr <8 x i32> %t0, %nbits
+ %t2 = and <8 x i32> %t1, %x
+ %t3 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+ call void @use8xi32(<8 x i32> %t0)
+ call void @use8xi32(<8 x i32> %t1)
+ call void @use8xi32(<8 x i32> %t3)
+ %t4 = shl <8 x i32> %t2, %t3 ; shift is smaller than mask
+ ret <8 x i32> %t4
+}
+
define <8 x i32> @t2_vec_nonsplat(<8 x i32> %x, <8 x i32> %nbits) {
; CHECK-LABEL: @t2_vec_nonsplat(
; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, [[NBITS:%.*]]
ret <8 x i32> %t3
}
+define <8 x i32> @t1_vec_splat_undef(<8 x i32> %x, <8 x i32> %nbits) {
+; CHECK-LABEL: @t1_vec_splat_undef(
+; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> [[X:%.*]], [[NBITS:%.*]]
+; CHECK-NEXT: [[T2:%.*]] = add <8 x i32> [[NBITS]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
+; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T2]])
+; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X]], [[T2]]
+; CHECK-NEXT: [[T3:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 -1, i32 2147483647>
+; CHECK-NEXT: ret <8 x i32> [[T3]]
+;
+ %t0 = shl <8 x i32> %x, %nbits
+ %t1 = lshr <8 x i32> %t0, %nbits
+ %t2 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
+ call void @use8xi32(<8 x i32> %t0)
+ call void @use8xi32(<8 x i32> %t2)
+ %t3 = shl <8 x i32> %t1, %t2 ; shift is smaller than mask
+ ret <8 x i32> %t3
+}
+
define <8 x i32> @t1_vec_nonsplat(<8 x i32> %x, <8 x i32> %nbits) {
; CHECK-LABEL: @t1_vec_nonsplat(
; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> [[X:%.*]], [[NBITS:%.*]]